Quickedu
commented
4 weeks ago I just fixed it by going into the folder "../h2o-llm studio/output/user" , making a copy of one of the experiments and rename it like the experiment that H2O was telling me that was missing in logs. :/
psinger
I had this error just after I started one experiment. When it happened first time, it crashed the whole thing. I have restarted H2O and tried to reinstall and get GitHub directories but it does not work. Now, when I run H2O, in screen Home, View Experiment and Create experiment, I see the same screen message (I upload screenshot of it).
This is the report H2O has given:
Report Issue: H2O LLM Studio at http://192.168.1.101:10101/
q.app script_sources: ['/_f/60417ac8-9c68-4bed-8f1c-f875e52f45ef/tmpftsu6rqn.min.js'] initialized: True version: 1.7.0-dev name: H2O LLM Studio heap_mode: False wave_utils_stack_trace_str: ### stacktrace Traceback (most recent call last):
File "/home/midue/h2o-llmstudio/./llm_studio/app_utils/handlers.py", line 78, in handle await home(q)
File "/home/midue/h2o-llmstudio/./llm_studio/app_utils/sections/home.py", line 21, in home experiments = get_experiments(q)
File "/home/midue/h2o-llmstudio/./llm_studio/app_utils/utils.py", line 1626, in get_experiments info = get_experiments_info(df, q)
File "/home/midue/h2o-llmstudio/./llm_studio/app_utils/utils.py", line 1449, in get_experiments_info with SqliteDict(f"{row.path}/charts.db") as logs:
File "/home/midue/llmstudio/lib/python3.10/site-packages/sqlitedict.py", line 157, in init raise RuntimeError('Error! The directory does not exist, %s' % dirname)
RuntimeError: Error! The directory does not exist, /home/midue/h2o-llmstudio/output/user/B.1.4.1.2_Casual-Modeling_h2oai-h2o-danube2-i.8b-base_Val.Size0.2_832-832-1664_bfloat16_LRate0.01_DiffLRate0.001_WarmEpoch1_Batch12_Epoch100_BLEU_AllDropout0.2NumBeams-3.1
q.user q.client app_db: <llm_studio.app_utils.db.Database object at 0x74b06815bfd0> client_initialized: True mode_curr: error theme_dark: True credential_saver: .env File default_aws_bucket_name: bucket_name default_azure_conn_string: default_azure_container: default_kaggle_username: set_max_epochs: 1000 set_max_batch_size: 256 set_max_gradient_clip: 10 set_max_lora_r: 256 set_max_lora_alpha: 256 gpu_used_for_chat: 1 default_number_of_workers: 8 default_logger: None default_neptune_project: default_openai_azure: False default_openai_api_base: https://example-endpoint.openai.azure.com default_openai_api_deployment_id: deployment-name default_openai_api_version: 2023-05-15 default_gpt_eval_max: 100 default_safe_serialization: True delete_dialogs: True chart_plot_max_points: 1000 init_interface: True notification_bar: None nav/active: home home: False report_error: True wave_submission_name: report_error q.events q.args report_error: True wave_submission_name: report_error stacktrace Traceback (most recent call last):
File “/home/midue/h2o-llmstudio/./llm_studio/app_utils/handlers.py”, line 78, in handle await home(q)
File “/home/midue/h2o-llmstudio/./llm_studio/app_utils/sections/home.py”, line 21, in home experiments = get_experiments(q)
File “/home/midue/h2o-llmstudio/./llm_studio/app_utils/utils.py”, line 1626, in get_experiments info = get_experiments_info(df, q)
File “/home/midue/h2o-llmstudio/./llm_studio/app_utils/utils.py”, line 1449, in get_experiments_info with SqliteDict(f"{row.path}/charts.db") as logs:
File “/home/midue/llmstudio/lib/python3.10/site-packages/sqlitedict.py”, line 157, in init raise RuntimeError(‘Error! The directory does not exist, %s’ % dirname)
RuntimeError: Error! The directory does not exist, /home/midue/h2o-llmstudio/output/user/B.1.4.1.2_Casual-Modeling_h2oai-h2o-danube2-i.8b-base_Val.Size0.2_832-832-1664_bfloat16_LRate0.01_DiffLRate0.001_WarmEpoch1_Batch12_Epoch100_BLEU_AllDropout0.2NumBeams-3.1
Error None
Git Version 6020ee4312a066a63004d7b8093653aae788a816